AI text-to-speech overview

AI Text-to-Speech (TTS) turns written text into lifelike audio. Use it for IVR prompts, queue announcements, music-on-hold messages, and AI Receptionist greetings — no recording booth required.

Why use it

• Speed. Update a prompt by editing one line of text instead of re-recording.
• Consistency. One voice across every menu, queue, and greeting.
• Multilingual. Generate the same prompt in every language you serve.

Where you can use TTS audio

• AI Receptionist greetings.
• IVR prompts and submenu prompts.
• Queue announcements (position, wait time, after-hours).
• Ring group prompts.
• Music on hold (spoken messages between music tracks).
• Call Flow Designer "Play" nodes.

Voices

The Drömlik voice library includes standard and neural voices in every supported language. Neural voices sound more natural but consume slightly more of your monthly TTS quota.

Next step

Generate AI voice prompts — step-by-step instructions for creating, previewing, and assigning a TTS audio file.